Real-time tool segmentation from endoscopic videos is an essential part of many computer-assisted robotic surgical systems and of critical importance in robotic surgical data science. We propose two novel deep learning architectures for automatic segmentation of non-rigid surgical instruments. Both methods take advantage of automated deep-learning-based multi-scale feature extraction while trying to maintain an accurate segmentation quality at all resolutions. The two proposed methods encode the multi-scale constraint inside the network architecture. The first proposed architecture enforces it by cascaded aggregation of predictions and the second proposed network does it by means of a holistically-nested architecture where the loss at each scale is taken into account for the optimization process. As the proposed methods are for real-time semantic labeling, both present a reduced number of parameters. We propose the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization of the network while maintaining the segmentation accuracy. We compare the proposed architectures against state-of-the-art fully convolutional networks. We validate our methods using existing benchmark datasets, including ex vivo cases with phantom tissue and different robotic surgical instruments present in the scene. Our results show a statistically significant improved Dice Similarity Coefficient over previous instrument segmentation methods. We analyze our design choices and discuss the key drivers for improving accuracy.

Increased demand for less invasive procedures has accelerated the adoption of Intraluminal Procedures (IP) and Endovascular Interventions (EI) performed through body lumens and vessels. As navigation through lumens and vessels is quite complex, interest grows to establish autonomous navigation techniques for IP and EI for reaching the target area. Current research efforts are directed toward increasing the Level of Autonomy (LoA) during the navigation phase. One key ingredient for autonomous navigation is Motion Planning (MP) techniques. This paper provides an overview of MP techniques categorizing them based on LoA. Our analysis investigates advances for the different clinical scenarios. Through a systematic literature analysis using the PRISMA method, the study summarizes relevant works and investigates the clinical aim, LoA, adopted MP techniques, and validation types. We identify the limitations of the corresponding MP methods and provide directions to improve the robustness of the algorithms in dynamic intraluminal environments. MP for IP and EI can be classified into four subgroups: node, sampling, optimization, and learning-based techniques, with a notable rise in learning-based approaches in recent years. One of the review's contributions is the identification of the limiting factors in IP and EI robotic systems hindering higher levels of autonomous navigation. In the future, navigation is bound to become more autonomous, placing the clinician in a supervisory position to improve control precision and reduce workload.

Fiber optic shape sensing is gaining popularity within areas such as medical catheterization where catheters and guidewires are used to navigate through tortuous vascular paths. Shape sensing can aid medical interventionalists by reducing damaging radiation and providing a more detailed real-time understanding of the 3-dimensional shape of the catheter/guidewire. However, despite the technology existing for several years, there is still room for improvement and steps to follow to reach the accuracy and robustness needed for these safety-critical applications. This paper discusses and provides methods for fiber integration within catheters to improve shape estimation accuracy and repeatability. A two-step calibration process is introduced for intrinsic twist compensation. This results in significant improvements in estimation accuracy. Additionally, a practical method for fiber parameter identification is introduced. The importance of estimating these parameters was found to be paramount for reaching adequate shape estimation. Further improvements to the reconstruction algorithm are proposed. Experimental validations with ground truth shapes are performed to assess the overall accuracy for static and dynamic configurations. For complex geometrical shapes and a fiber length of 170 mm, experiments show a mean spatial error of 0.70 mm (0.41%), a maximum of 2.52 mm (1.48%), and repeatability of ±0.82 mm.